Machine Learning for Rapid Magnetic Resonance Fingerprinting Tissue Property Quantification

Fast Whole-Brain MR Multi-Parametric Mapping with Scan-Specific Self-Supervised Networks

Quantification of tissue parameters using MRI is emerging as a powerful tool in clinical diagnosis and research studies. The need for multiple long scans with different acquisition parameters prohibits quantitative MRI from reaching widespread adoption in routine clinical and research exams. Accelerated parameter mapping techniques leverage parallel imaging, signal modelling and deep learning to offer more practical quantitative MRI acquisitions. However, the achievable acceleration and the quality of maps are often limited. Joint MAPLE is a recent state-of-the-art multi-parametric and scan-specific parameter mapping technique with promising performance at high acceleration rates. It synergistically combines parallel imaging, model-based and machine learning approaches for joint mapping ofT 1 , T 2 * , proton density and the field inhomogeneity. However, Joint MAPLE suffers from prohibitively long reconstruction time to estimate the maps from a multi-echo, multi-flip angle (MEMFA) dataset at high resolution in a scan-specific manner. In this work, we propose a faster version of Joint MAPLE which retains the mapping performance of the original version. Coil compression, random slice selection, parameter-specific learning rates and transfer learning are synergistically combined in the proposed framework. It speeds-up the reconstruction time up to 700 times than the original version and processes a whole-brain MEMFA dataset in 21 minutes on average, which originally requires ~260 hours for Joint MAPLE. The mapping performance of the proposed framework is ~2-fold better than the standard and the state-of-the-art evaluated reconstruction techniques on average in terms of the root mean squared error.

Recurrent neural network-based simultaneous cardiac T1, T2, and T1ρ mapping

The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free-breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN-based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN-based method was compared with a dictionary-matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN-based method and the dictionary-matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN-based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60-fold acceleration compared with the dictionary-matching method. The RNN-accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary-matching method for the free-breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications.

Joint MAPLE: Accelerated joint T1 and T 2 * $$ {{\mathrm{T}}_2}^{\ast } $$ mapping with scan-specific self-supervised networks

PURPOSE

Quantitative MRI finds important applications in clinical and research studies. However, it is encoding intensive and may suffer from prohibitively long scan times. Accelerated MR parameter mapping techniques have been developed to help address these challenges. Here, an accelerated joint T1,T 2 * $$ {{\mathrm{T}}_2}^{\ast } $$ , frequency and proton density mapping technique with scan-specific self-supervised network reconstruction is proposed to synergistically combine parallel imaging, model-based, and deep learning approaches to speed up parameter mapping.

METHODS

Proposed framework, Joint MAPLE, includes parallel imaging, signal modeling, and data consistency blocks which are optimized jointly in a combined loss function. A scan-specific self-supervised reconstruction is embedded into the framework, which takes advantage of multi-contrast data from a multi-echo, multi-flip angle, gradient echo acquisition.

RESULTS

In comparison with parallel reconstruction techniques powered by low-rank methods, emerging scan specific networks, and model-basedT 2 * $$ {{\mathrm{T}}_2}^{\ast } $$ estimation approaches, the proposed framework reduces the reconstruction error in parameter maps by approximately two-fold on average at acceleration rates as high as R = 16 with uniform sampling. It can outperform evaluated parallel reconstruction techniques up to four-fold on average in the presence of challenging sub-sampling masks. It is observed that Joint MAPLE performs well at extreme acceleration rates of R = 25 and R = 36 with error values less than 20%.

CONCLUSION

Joint MAPLE enables higher fidelity parameter estimation at high acceleration rates by synergistically combining parallel imaging and model-based parameter mapping and exploiting multi-echo, multi-flip angle datasets. Utilizing a scan-specific self-supervised reconstruction obviates the need for large data sets for training while improving the parameter estimation ability.

Accelerated liver water T1 mapping using single-shot continuous inversion-recovery spiral imaging

PURPOSE

Liver T1 mapping techniques typically require long breath holds or long scan time in free-breathing, need correction for B 1 + inhomogeneities and process composite (water and fat) signals. The purpose of this work is to accelerate the multi-slice acquisition of liver water selective T1 (wT1) mapping in a single breath hold, improving the k-space sampling efficiency.

METHODS

The proposed continuous inversion-recovery (IR) Look-Locker methodology combines a single-shot gradient echo spiral readout, Dixon processing and a dictionary-based analysis for liver wT1 mapping at 3 T. The sequence parameters were adapted to obtain short scan times. The influence of fat, B 1 + inhomogeneities and TE on the estimation of T1 was first assessed using simulations. The proposed method was then validated in a phantom and in 10 volunteers, comparing it with MRS and the modified Look-Locker inversion-recovery (MOLLI) method. Finally, the clinical feasibility was investigated by comparing wT1 maps with clinical scans in nine patients.

RESULTS

The phantom results are in good agreement with MRS. The proposed method encodes the IR-curve for the liver wT1 estimation, is minimally sensitive to B 1 + inhomogeneities and acquires one slice in 1.2 s. The volunteer results confirmed the multi-slice capability of the proposed method, acquiring nine slices in a breath hold of 11 s. The present work shows robustness to B 1 + inhomogeneities (wT 1 , No B 1 + = 1.07 wT 1 , B 1 + - 45.63 , R 2 = 0.99 ) , good repeatability (wT 1 , 2 ° = 1 . 0 wT 1 , 1 ° - 2.14 , R 2 = 0.96 ) and is in better agreement with MRS (wT 1 = 0.92 wT 1 MRS + 103.28 , R 2 = 0.38 ) than is MOLLI (wT 1 MOLLI = 0.76 wT 1 MRS + 254.43 , R 2 = 0.44 ) . The wT1 maps in patients captured diverse lesions, thus showing their clinical feasibility.

CONCLUSION

A single-shot spiral acquisition can be combined with a continuous IR Look-Locker method to perform rapid repeatable multi-slice liver water T1 mapping at a rate of 1.2 s per slice without a B 1 + map. The proposed method is suitable for nine-slice liver clinical applications acquired in a single breath hold of 11 s.

Deep learning-assisted preclinical MR fingerprinting for sub-millimeter T1 and T2 mapping of entire macaque brain

PURPOSE

Preclinical MR fingerprinting (MRF) suffers from long acquisition time for organ-level coverage due to demanding image resolution and limited undersampling capacity. This study aims to develop a deep learning-assisted fast MRF framework for sub-millimeter T1 and T2 mapping of entire macaque brain on a preclinical 9.4 T MR system.

METHODS

Three dimensional MRF images were reconstructed by singular value decomposition (SVD) compressed reconstruction. T1 and T2 mapping for each axial slice exploited a self-attention assisted residual U-Net to suppress aliasing-induced quantification errors, and the transmit-field (B1 + ) measurements for robustness against B1 + inhomogeneity. Supervised network training used MRF images simulated via virtual parametric maps and a desired undersampling scheme. This strategy bypassed the difficulties of acquiring fully sampled preclinical MRF data to guide network training. The proposed fast MRF framework was tested on experimental data acquired from ex vivo and in vivo macaque brains.

RESULTS

The trained network showed reasonable adaptability to experimental MRF images, enabling robust delineation of various T1 and T2 distributions in the brain tissues. Further, the proposed MRF framework outperformed several existing fast MRF methods in handling the aliasing artifacts and capturing detailed cerebral structures in the mapping results. Parametric mapping of entire macaque brain at nominal resolution of 0.35× $$ \times $$ 0.35× $$ \times $$ 1 mm3 can be realized via a 20-min 3D MRF scan, which was sixfold faster than the baseline protocol.

CONCLUSION

Introducing deep learning to MRF framework paves the way for efficient organ-level high-resolution quantitative MRI in preclinical applications.

Cardiac MR Fingerprinting: Overview, Technical Developments, and Applications

Cardiovascular magnetic resonance (CMR) is an established imaging modality with proven utility in assessing cardiovascular diseases. The ability of CMR to characterize myocardial tissue using T1 - and T2 -weighted imaging, parametric mapping, and late gadolinium enhancement has allowed for the non-invasive identification of specific pathologies not previously possible with modalities like echocardiography. However, CMR examinations are lengthy and technically complex, requiring multiple pulse sequences and different anatomical planes to comprehensively assess myocardial structure, function, and tissue composition. To increase the overall impact of this modality, there is a need to simplify and shorten CMR exams to improve access and efficiency, while also providing reproducible quantitative measurements. Multiparametric MRI techniques that measure multiple tissue properties offer one potential solution to this problem. This review provides an in-depth look at one such multiparametric approach, cardiac magnetic resonance fingerprinting (MRF). The article is structured as follows. First, a brief review of single-parametric and (non-Fingerprinting) multiparametric CMR mapping techniques is presented. Second, a general overview of cardiac MRF is provided covering pulse sequence implementation, dictionary generation, fast k-space sampling methods, and pattern recognition. Third, recent technical advances in cardiac MRF are covered spanning a variety of topics, including simultaneous multislice and 3D sampling, motion correction algorithms, cine MRF, synthetic multicontrast imaging, extensions to measure additional clinically important tissue properties (proton density fat fraction, T2 *, and T1ρ ), and deep learning methods for image reconstruction and parameter estimation. The last section will discuss potential clinical applications, concluding with a perspective on how multiparametric techniques like MRF may enable streamlined CMR protocols. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

Motion-compensated T1 mapping in cardiovascular magnetic resonance imaging: a technical review

T 1 mapping is becoming a staple magnetic resonance imaging method for diagnosing myocardial diseases such as ischemic cardiomyopathy, hypertrophic cardiomyopathy, myocarditis, and more. Clinically, most T 1 mapping sequences acquire a single slice at a single cardiac phase across a 10 to 15-heartbeat breath-hold, with one to three slices acquired in total. This leaves opportunities for improving patient comfort and information density by acquiring data across multiple cardiac phases in free-running acquisitions and across multiple respiratory phases in free-breathing acquisitions. Scanning in the presence of cardiac and respiratory motion requires more complex motion characterization and compensation. Most clinical mapping sequences use 2D single-slice acquisitions; however newer techniques allow for motion-compensated reconstructions in three dimensions and beyond. To further address confounding factors and improve measurement accuracy, T 1 maps can be acquired jointly with other quantitative parameters such as T 2 , T 2 ∗ , fat fraction, and more. These multiparametric acquisitions allow for constrained reconstruction approaches that isolate contributions to T 1 from other motion and relaxation mechanisms. In this review, we examine the state of the literature in motion-corrected and motion-resolved T 1 mapping, with potential future directions for further technical development and clinical translation.

Magnetic Resonance Fingerprinting: A Review of Clinical Applications

ABSTRACT

Magnetic resonance fingerprinting (MRF) is an approach to quantitative magnetic resonance imaging that allows for efficient simultaneous measurements of multiple tissue properties, which are then used to create accurate and reproducible quantitative maps of these properties. As the technique has gained popularity, the extent of preclinical and clinical applications has vastly increased. The goal of this review is to provide an overview of currently investigated preclinical and clinical applications of MRF, as well as future directions. Topics covered include MRF in neuroimaging, neurovascular, prostate, liver, kidney, breast, abdominal quantitative imaging, cardiac, and musculoskeletal applications.

Assessment of MRF for simultaneous T1 and T2 quantification and water-fat separation in the liver at 0.55 T

OBJECTIVE

The goal of this work was to assess the feasibility of performing MRF in the liver on a 0.55 T scanner and to examine the feasibility of water-fat separation using rosette MRF at 0.55 T.

MATERIALS AND METHODS

Spiral and rosette MRF sequences were implemented on a commercial 0.55 T scanner. The accuracy of both sequences in T1 and T2 quantification was validated in the ISMRM/NIST system phantom. The efficacy of rosette MRF in water-fat separation was evaluated in simulations and water/oil phantoms. Both spiral and rosette MRF were performed in the liver of healthy subjects.

RESULTS

In the ISMRM/NIST phantom, both spiral and rosette MRF achieved good agreement with reference values in T1 and T2 measurements. In addition, rosette MRF enables water-fat separation and can generate water- and fat- specific T1 maps, T2 maps, and proton density images from the same dataset for a spatial resolution of 1.56 × 1.56 × 5mm3 within the acquisition time of 15 s.

CONCLUSION

It is feasible to measure T1 and T2 simultaneously in the liver using MRF on a 0.55 T system with lower performance gradients compared to state-of-the-art 1.5 T and 3 T systems within an acquisition time of 15 s. In addition, rosette MRF enables water-fat separation along with T1 and T2 quantification with no time penalty.

Accelerated and quantitative three-dimensional molecular MRI using a generative adversarial network

PURPOSE

To substantially shorten the acquisition time required for quantitative three-dimensional (3D) chemical exchange saturation transfer (CEST) and semisolid magnetization transfer (MT) imaging and allow for rapid chemical exchange parameter map reconstruction.

METHODS

Three-dimensional CEST and MT magnetic resonance fingerprinting (MRF) datasets of L-arginine phantoms, whole-brains, and calf muscles from healthy volunteers, cancer patients, and cardiac patients were acquired using 3T clinical scanners at three different sites, using three different scanner models and coils. A saturation transfer-oriented generative adversarial network (GAN-ST) supervised framework was then designed and trained to learn the mapping from a reduced input data space to the quantitative exchange parameter space, while preserving perceptual and quantitative content.

RESULTS

The GAN-ST 3D acquisition time was 42-52 s, 70% shorter than CEST-MRF. The quantitative reconstruction of the entire brain took 0.8 s. An excellent agreement was observed between the ground truth and GAN-based L-arginine concentration and pH values (Pearson's r > 0.95, ICC > 0.88, NRMSE < 3%). GAN-ST images from a brain-tumor subject yielded a semi-solid volume fraction and exchange rate NRMSE of3 . 8 ± 1 . 3 % $$ 3.8\pm 1.3\% $$ and4 . 6 ± 1 . 3 % $$ 4.6\pm 1.3\% $$ , respectively, and SSIM of96 . 3 ± 1 . 6 % $$ 96.3\pm 1.6\% $$ and95 . 0 ± 2 . 4 % $$ 95.0\pm 2.4\% $$ , respectively. The mapping of the calf-muscle exchange parameters in a cardiac patient, yielded NRMSE < 7% and SSIM > 94% for the semi-solid exchange parameters. In regions with large susceptibility artifacts, GAN-ST has demonstrated improved performance and reduced noise compared to MRF.

CONCLUSION

GAN-ST can substantially reduce the acquisition time for quantitative semi-solid MT/CEST mapping, while retaining performance even when facing pathologies and scanner models that were not available during training.

GPU accelerated grouped magnetic resonance fingerprinting using clustering techniques

Magnetic Resonance Fingerprinting (MRF) is a new quantitative technique of Magnetic Resonance Imaging (MRI). Conventionally, MRF requires sequential correlation of the acquired MRF signals with all the signals of (a large sized) MRF dictionary. This is a computationally intensive matching process and is a major challenge in MRF image reconstruction. This paper introduces the use of clustering techniques (to reduce the effective size of MRF dictionary) by splitting MRF dictionary into multiple small sized MRF dictionary components called MRF signal groups. The proposed method has been further optimized for parallel processing to reduce the computation time of MRF pattern matching. A multi-core GPU based parallel framework has been developed that enables the MRF algorithm to process multiple MRF signals simultaneously. Experiments have been performed on human head and phantom datasets. The results show that the proposed method accelerates the conventional MRF (MATLAB based) reconstruction time up to 25× with single-core CPU implementation, 300× with multi- core CPU implementation and 1035× with the proposed multi-core GPU based framework by keeping the SNR of the resulting images in a clinically acceptable range. Furthermore, experimental results show that the memory requirements of MRF dictionary get significantly reduced (due to efficient memory utilization) in the proposed method.

Imaging biomarkers for clinical applications in neuro-oncology: current status and future perspectives

Biomarker discovery and development are popular for detecting the subtle diseases. However, biomarkers are needed to be validated and approved, and even fewer are ever used clinically. Imaging biomarkers have a crucial role in the treatment of cancer patients because they provide objective information on tumor biology, the tumor's habitat, and the tumor's signature in the environment. Tumor changes in response to an intervention complement molecular and genomic translational diagnosis as well as quantitative information. Neuro-oncology has become more prominent in diagnostics and targeted therapies. The classification of tumors has been actively updated, and drug discovery, and delivery in nanoimmunotherapies are advancing in the field of target therapy research. It is important that biomarkers and diagnostic implements be developed and used to assess the prognosis or late effects of long-term survivors. An improved realization of cancer biology has transformed its management with an increasing emphasis on a personalized approach in precision medicine. In the first part, we discuss the biomarker categories in relation to the courses of a disease and specific clinical contexts, including that patients and specimens should both directly reflect the target population and intended use. In the second part, we present the CT perfusion approach that provides quantitative and qualitative data that has been successfully applied to the clinical diagnosis, treatment and application. Furthermore, the novel and promising multiparametric MR imageing approach will provide deeper insights regarding the tumor microenvironment in the immune response. Additionally, we briefly remark new tactics based on MRI and PET for converging on imaging biomarkers combined with applications of bioinformatics in artificial intelligence. In the third part, we briefly address new approaches based on theranostics in precision medicine. These sophisticated techniques merge achievable standardizations into an applicatory apparatus for primarily a diagnostic implementation and tracking radioactive drugs to identify and to deliver therapies in an individualized medicine paradigm. In this article, we describe the critical principles for imaging biomarker characterization and discuss the current status of CT, MRI and PET in finiding imaging biomarkers of early disease.

Cardiac Magnetic Resonance Fingerprinting: Potential Clinical Applications

PURPOSE OF REVIEW

Cardiac magnetic resonance fingerprinting (cMRF) has developed as a technique for rapid, multi-parametric tissue property mapping that has potential to both improve cardiac MRI exam efficiency and expand the information captured. In this review, we describe the cMRF technique, summarize technical developments and in vivo reports, and highlight potential clinical applications.

RECENT FINDINGS

Technical developments in cMRF continue to progress rapidly, including motion compensated reconstruction, additional tissue property quantification, signal time course analysis, and synthetic LGE image generation. Such technical developments can enable simplified CMR protocols by combining multiple evaluations into a single protocol and reducing the number of breath-held scans. cMRF continues to be reported for use in a range of pathologies; however barriers to clinical implementation remain. Technical developments are described in this review, followed by a focus on potential clinical applications that they may support. Clinical translation of cMRF could shorten protocols, improve CMR accessibility, and provide additional information as compared to conventional cardiac parametric mapping methods. Current needs for clinical implementation are discussed, as well as how those needs may be met in order to bring cMRF from its current research setting to become a viable tool for patient care.

Dynamic Cardiac Magnetic Resonance Fingerprinting During Vasoactive Breathing Maneuvers: First Results

BACKGROUND

Cardiac magnetic resonance fingerprinting (cMRF) enables simultaneous mapping of myocardial T1 and T2 with very short acquisition times. Breathing maneuvers have been utilized as a vasoactive stress test to dynamically characterize myocardial tissue in vivo. We tested the feasibility of sequential, rapid cMRF acquisitions during breathing maneuvers to quantify myocardial T1 and T2 changes.

METHODS

We measured T1 and T2 values using conventional T1 and T2-mapping techniques (modified look locker inversion [MOLLI] and T2-prepared balanced-steady state free precession), and a 15 heartbeat (15-hb) and rapid 5-hb cMRF sequence in a phantom and in 9 healthy volunteers. The cMRF_5-hb sequence was also used to dynamically assess T1 and T2 changes over the course of a vasoactive combined breathing maneuver.

RESULTS

In healthy volunteers, the mean myocardial T1 of the different mapping methodologies were: MOLLI 1,224 ± 81 ms, cMRF_15-hb 1,359 ± 97 ms, and cMRF_5-hb 1,357 ± 76 ms. The mean myocardial T2 measured with the conventional mapping technique was 41.7 ± 6.7 ms, while for cMRF_15-hb 29.6 ± 5.8 ms and cMRF_5-hb 30.5 ± 5.8 ms. T2 was reduced with vasoconstriction (post-hyperventilation compared to a baseline resting state) (30.15 ± 1.53 ms vs. 27.99 ± 2.07 ms, p = 0.02), while T1 did not change with hyperventilation. During the vasodilatory breath-hold, no significant change of myocardial T1 and T2 was observed.

CONCLUSIONS

cMRF_5-hb enables simultaneous mapping of myocardial T1 and T2, and may be used to track dynamic changes of myocardial T1 and T2 during vasoactive combined breathing maneuvers.

Simultaneous multi-parametric acquisition and reconstruction techniques in cardiac magnetic resonance imaging: Basic concepts and status of clinical development

Simultaneous multi-parametric acquisition and reconstruction techniques (SMART) are gaining attention for their potential to overcome some of cardiovascular magnetic resonance imaging's (CMR) clinical limitations. The major advantages of SMART lie within their ability to simultaneously capture multiple "features" such as cardiac motion, respiratory motion, T1/T2 relaxation. This review aims to summarize the overarching theory of SMART, describing key concepts that many of these techniques share to produce co-registered, high quality CMR images in less time and with less requirements for specialized personnel. Further, this review provides an overview of the recent developments in the field of SMART by describing how they work, the parameters they can acquire, their status of clinical testing and validation, and by providing examples for how their use can improve the current state of clinical CMR workflows. Many of the SMART are in early phases of development and testing, thus larger scale, controlled trials are needed to evaluate their use in clinical setting and with different cardiac pathologies.

Acceleration Strategies for MR-STAT: Achieving High-Resolution Reconstructions on a Desktop PC Within 3 Minutes

MR-STAT is an emerging quantitative magnetic resonance imaging technique which aims at obtaining multi-parametric tissue parameter maps from single short scans. It describes the relationship between the spatial-domain tissue parameters and the time-domain measured signal by using a comprehensive, volumetric forward model. The MR-STAT reconstruction solves a large-scale nonlinear problem, thus is very computationally challenging. In previous work, MR-STAT reconstruction using Cartesian readout data was accelerated by approximating the Hessian matrix with sparse, banded blocks, and can be done on high performance CPU clusters with tens of minutes. In the current work, we propose an accelerated Cartesian MR-STAT algorithm incorporating two different strategies: firstly, a neural network is trained as a fast surrogate to learn the magnetization signal not only in the full time-domain but also in the compressed low-rank domain; secondly, based on the surrogate model, the Cartesian MR-STAT problem is re-formulated and split into smaller sub-problems by the alternating direction method of multipliers. The proposed method substantially reduces the computational requirements for runtime and memory. Simulated and in-vivo balanced MR-STAT experiments show similar reconstruction results using the proposed algorithm compared to the previous sparse Hessian method, and the reconstruction times are at least 40 times shorter. Incorporating sensitivity encoding and regularization terms is straightforward, and allows for better image quality with a negligible increase in reconstruction time. The proposed algorithm could reconstruct both balanced and gradient-spoiled in-vivo data within 3 minutes on a desktop PC, and could thereby facilitate the translation of MR-STAT in clinical settings.

Artificial intelligence in cardiac magnetic resonance fingerprinting

Magnetic resonance fingerprinting (MRF) is a fast MRI-based technique that allows for multiparametric quantitative characterization of the tissues of interest in a single acquisition. In particular, it has gained attention in the field of cardiac imaging due to its ability to provide simultaneous and co-registered myocardial T₁ and T₂ mapping in a single breath-held cardiac MRF scan, in addition to other parameters. Initial results in small healthy subject groups and clinical studies have demonstrated the feasibility and potential of MRF imaging. Ongoing research is being conducted to improve the accuracy, efficiency, and robustness of cardiac MRF. However, these improvements usually increase the complexity of image reconstruction and dictionary generation and introduce the need for sequence optimization. Each of these steps increase the computational demand and processing time of MRF. The latest advances in artificial intelligence (AI), including progress in deep learning and the development of neural networks for MRI, now present an opportunity to efficiently address these issues. Artificial intelligence can be used to optimize candidate sequences and reduce the memory demand and computational time required for reconstruction and post-processing. Recently, proposed machine learning-based approaches have been shown to reduce dictionary generation and reconstruction times by several orders of magnitude. Such applications of AI should help to remove these bottlenecks and speed up cardiac MRF, improving its practical utility and allowing for its potential inclusion in clinical routine. This review aims to summarize the latest developments in artificial intelligence applied to cardiac MRF. Particularly, we focus on the application of machine learning at different steps of the MRF process, such as sequence optimization, dictionary generation and image reconstruction.

MR fingerprinting of the prostate

Multiparametric magnetic resonance imaging (mpMRI) has been adopted as the key tool for detection, localization, characterization, and risk stratification of patients suspected to have prostate cancer. Despite advantages over systematic biopsy, the interpretation of prostate mpMRI has limitations including a steep learning curve, leading to considerable interobserver variation. There is growing interest in clinical translation of quantitative imaging techniques for more objective lesion assessment. However, traditional mapping techniques are slow, precluding their use in the clinic. Magnetic resonance fingerprinting (MRF) is an efficient approach for quantitative maps of multiple tissue properties simultaneously. The T1 and T2 values obtained with MRF have been validated with phantom studies as well as in normal volunteers and patients. Studies have shown that MRF-derived T1 and T2 along with ADC values are all significant independent predictors in the differentiation between normal prostate tissue and prostate cancer, and hold promise in differentiating low and intermediate/high-grade cancers. This review seeks to introduce the basics of the prostate MRF technique, discuss the potential applications of prostate MRF for the characterization of prostate cancer, and describes ongoing areas of research.

Cramér-Rao bound-informed training of neural networks for quantitative MRI

PURPOSE

To improve the performance of neural networks for parameter estimation in quantitative MRI, in particular when the noise propagation varies throughout the space of biophysical parameters.

THEORY AND METHODS

A theoretically well-founded loss function is proposed that normalizes the squared error of each estimate with respective Cramér-Rao bound (CRB)-a theoretical lower bound for the variance of an unbiased estimator. This avoids a dominance of hard-to-estimate parameters and areas in parameter space, which are often of little interest. The normalization with corresponding CRB balances the large errors of fundamentally more noisy estimates and the small errors of fundamentally less noisy estimates, allowing the network to better learn to estimate the latter. Further, proposed loss function provides an absolute evaluation metric for performance: A network has an average loss of 1 if it is a maximally efficient unbiased estimator, which can be considered the ideal performance. The performance gain with proposed loss function is demonstrated at the example of an eight-parameter magnetization transfer model that is fitted to phantom and in vivo data.

RESULTS

Networks trained with proposed loss function perform close to optimal, that is, their loss converges to approximately 1, and their performance is superior to networks trained with the standard mean-squared error (MSE). The proposed loss function reduces the bias of the estimates compared to the MSE loss, and improves the match of the noise variance to the CRB. This performance gain translates to in vivo maps that align better with the literature.

CONCLUSION

Normalizing the squared error with the CRB during the training of neural networks improves their performance in estimating biophysical parameters.

A Self-Supervised Deep Learning Reconstruction for Shortening the Breathhold and Acquisition Window in Cardiac Magnetic Resonance Fingerprinting

The aim of this study is to shorten the breathhold and diastolic acquisition window in cardiac magnetic resonance fingerprinting (MRF) for simultaneous T1, T2, and proton spin density (M0) mapping to improve scan efficiency and reduce motion artifacts. To this end, a novel reconstruction was developed that combines low-rank subspace modeling with a deep image prior, termed DIP-MRF. A system of neural networks is used to generate spatial basis images and quantitative tissue property maps, with training performed using only the undersampled k-space measurements from the current scan. This approach avoids difficulties with obtaining in vivo MRF training data, as training is performed de novo for each acquisition. Calculation of the forward model during training is accelerated by using GRAPPA operator gridding to shift spiral k-space data to Cartesian grid points, and by using a neural network to rapidly generate fingerprints in place of a Bloch equation simulation. DIP-MRF was evaluated in simulations and at 1.5 T in a standardized phantom, 18 healthy subjects, and 10 patients with suspected cardiomyopathy. In addition to conventional mapping, two cardiac MRF sequences were acquired, one with a 15-heartbeat(HB) breathhold and 254 ms acquisition window, and one with a 5HB breathhold and 150 ms acquisition window. In simulations, DIP-MRF yielded decreased nRMSE compared to dictionary matching and a sparse and locally low rank (SLLR-MRF) reconstruction. Strong correlation (R2 &gt; 0.999) with T1 and T2 reference values was observed in the phantom using the 5HB/150 ms scan with DIP-MRF. DIP-MRF provided better suppression of noise and aliasing artifacts in vivo, especially for the 5HB/150 ms scan, and lower intersubject and intrasubject variability compared to dictionary matching and SLLR-MRF. Furthermore, it yielded a better agreement between myocardial T1 and T2 from 15HB/254 ms and 5HB/150 ms MRF scans, with a bias of −9 ms for T1 and 2 ms for T2. In summary, this study introduces an extension of the deep image prior framework for cardiac MRF tissue property mapping, which does not require pre-training with in vivo scans, and has the potential to reduce motion artifacts by enabling a shortened breathhold and acquisition window.

Rapid MR relaxometry using deep learning: An overview of current techniques and emerging trends

Quantitative mapping of MR tissue parameters such as the spin-lattice relaxation time (T1 ), the spin-spin relaxation time (T2 ), and the spin-lattice relaxation in the rotating frame (T1ρ ), referred to as MR relaxometry in general, has demonstrated improved assessment in a wide range of clinical applications. Compared with conventional contrast-weighted (eg T1 -, T2 -, or T1ρ -weighted) MRI, MR relaxometry provides increased sensitivity to pathologies and delivers important information that can be more specific to tissue composition and microenvironment. The rise of deep learning in the past several years has been revolutionizing many aspects of MRI research, including image reconstruction, image analysis, and disease diagnosis and prognosis. Although deep learning has also shown great potential for MR relaxometry and quantitative MRI in general, this research direction has been much less explored to date. The goal of this paper is to discuss the applications of deep learning for rapid MR relaxometry and to review emerging deep-learning-based techniques that can be applied to improve MR relaxometry in terms of imaging speed, image quality, and quantification robustness. The paper is comprised of an introduction and four more sections. Section 2 describes a summary of the imaging models of quantitative MR relaxometry. In Section 3, we review existing "classical" methods for accelerating MR relaxometry, including state-of-the-art spatiotemporal acceleration techniques, model-based reconstruction methods, and efficient parameter generation approaches. Section 4 then presents how deep learning can be used to improve MR relaxometry and how it is linked to conventional techniques. The final section concludes the review by discussing the promise and existing challenges of deep learning for rapid MR relaxometry and potential solutions to address these challenges.

Artificial intelligence and imaging: Opportunities in cardio-oncology

Cardiovascular disease is a leading cause of death in cancer survivors. It is critical to apply new predictive and early diagnostic methods in this population, as this can potentially inform cardiovascular treatment and surveillance decision-making. We discuss the application of artificial intelligence (AI) technologies to cardiovascular imaging in cardio-oncology, with a particular emphasis on prevention and targeted treatment of a variety of cardiovascular conditions in cancer patients. Recently, the use of AI-augmented cardiac imaging in cardio-oncology is gaining traction. A large proportion of cardio-oncology patients are screened and followed using left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS), currently obtained using echocardiography. This use will continue to increase with new cardiotoxic cancer treatments. AI is being tested to increase precision, throughput, and accuracy of LVEF and GLS, guide point-of-care image acquisition, and integrate imaging and clinical data to optimize the prediction and detection of cardiac dysfunction. The application of AI to cardiovascular magnetic resonance imaging (CMR), computed tomography (CT; especially coronary artery calcium or CAC scans), single proton emission computed tomography (SPECT) and positron emission tomography (PET) imaging acquisition is also in early stages of analysis for prediction and assessment of cardiac tumors and cardiovascular adverse events in patients treated for childhood or adult cancer. The opportunities for application of AI in cardio-oncology imaging are promising, and if availed, will improve clinical practice and benefit patient care.

Cartesian dictionary-based native T1 and T2 mapping of the myocardium

PURPOSE

To implement and evaluate a new dictionary-based technique for native myocardial T₁ and T₂ mapping using Cartesian sampling.

METHODS

The proposed technique (Multimapping) consisted of single-shot Cartesian image acquisitions in 10 consecutive cardiac cycles, with inversion pulses in cycle 1 and 5, and T₂ preparation (TE: 30 ms, 50 ms, and 70 ms) in cycles 8-10. Multimapping was simulated for different T₁ and T₂ , where entries corresponding to the k-space centers were matched to acquired data. Experiments were performed in a phantom, 16 healthy subjects, and 3 patients with cardiovascular disease.

RESULTS

Multimapping phantom measurements showed good agreement with reference values for both T₁ and T₂ , with no discernable heart-rate dependency for T₁ and T₂ within the range of myocardium. In vivo mean T₁ in healthy subjects was significantly higher using Multimapping (T₁ = 1114 ± 14 ms) compared to the reference (T₁ = 991 ± 26 ms) (p < 0.01). Mean Multimapping T₂ (47.1 ± 1.3 ms) and T₂ spatial variability (5.8 ± 1.0 ms) was significantly lower compared to the reference (T₂ = 54.7 ± 2.2 ms, p < 0.001; spatial variability = 8.4 ± 2.0 ms, p < 0.01). Increased T₁ and T₂ was detected in all patients using Multimapping.

CONCLUSIONS

Multimapping allows for simultaneous native myocardial T₁ and T₂ mapping with a conventional Cartesian trajectory, demonstrating promising in vivo image quality and parameter quantification results.

Simultaneous T1 , T2 , and T1ρ cardiac magnetic resonance fingerprinting for contrast agent-free myocardial tissue characterization

PURPOSE

To develop a simultaneous T₁ , T₂ , and T_1ρ cardiac magnetic resonance fingerprinting (MRF) approach to enable comprehensive contrast agent-free myocardial tissue characterization in a single breath-hold scan.

METHODS

A 2D gradient-echo electrocardiogram-triggered cardiac MRF sequence with low flip angles, varying magnetization preparation, and spiral trajectory was acquired at 1.5 T to encode T₁ , T₂ , and T_1⍴ simultaneously. The MRF images were reconstructed using low-rank inversion, regularized with a multicontrast patch-based higher-order reconstruction. Parametric maps were generated and matched in the singular value domain to extended phase graph-based dictionaries. The proposed approach was tested in phantoms and 10 healthy subjects and compared against conventional methods in terms of coefficients of determination and best fits for the phantom study, and in terms of Bland-Altman agreement, average values and coefficient of variation of T₁ , T₂ , and T_1⍴ for the healthy subjects study.

RESULTS

The T₁ , T₂ , and T_1⍴ MRF values showed excellent correlation with conventional spin-echo and clinical mapping methods in phantom studies (r² > 0.97). Measured MRF values in myocardial tissue (mean ± SD) were 1133 ± 33 ms, 38.8 ± 3.5 ms, and 52.0 ± 4.0 ms for T₁ , T₂ and T1_⍴ , respectively, against 1053 ± 47 ms, 50.4 ± 3.9 ms, and 55.9 ± 3.3 ms for T₁ modified Look-Locker inversion imaging, T₂ gradient and spin echo, and T_1⍴ turbo field echo, respectively.

CONCLUSION

A cardiac MRF approach for simultaneous quantification of myocardial T₁ , T₂ , and T_1ρ in a single breath-hold MR scan of about 16 seconds has been proposed. The approach has been investigated in phantoms and healthy subjects showing good agreement with reference spin echo measurements and conventional clinical maps.

A deep learning approach for magnetic resonance fingerprinting: Scaling capabilities and good training practices investigated by simulations

MR fingerprinting (MRF) is an innovative approach to quantitative MRI. A typical disadvantage of dictionary-based MRF is the explosive growth of the dictionary as a function of the number of reconstructed parameters, an instance of the curse of dimensionality, which determines an explosion of resource requirements. In this work, we describe a deep learning approach for MRF parameter map reconstruction using a fully connected architecture. Employing simulations, we have investigated how the performance of the Neural Networks (NN) approach scales with the number of parameters to be retrieved, compared to the standard dictionary approach. We have also studied optimal training procedures by comparing different strategies for noise addition and parameter space sampling, to achieve better accuracy and robustness to noise. Four MRF sequences were considered: IR-FISP, bSSFP, IR-FISP-B₁, and IR-bSSFP-B₁. A comparison between NN and the dictionary approaches in reconstructing parameter maps as a function of the number of parameters to be retrieved was performed using a numerical brain phantom. Results demonstrated that training with random sampling and different levels of noise variance yielded the best performance. NN performance was at least as good as the dictionary-based approach in reconstructing parameter maps using Gaussian noise as a source of artifacts: the difference in performance increased with the number of estimated parameters because the dictionary method suffers from the coarse resolution of the parameter space sampling. The NN proved to be more efficient in memory usage and computational burden, and has great potential for solving large-scale MRF problems.

Efficiency analysis for quantitative MRI of T1 and T2 relaxometry methods

This study presents a comparison of quantitative MRI methods based on an efficiency metric that quantifies their intrinsic ability to extract information about tissue parameters. Under a regime of unbiased parameter estimates, an intrinsic efficiency metricηwas derived for fully-sampled experiments which can be used to both optimize and compare sequences. Here we optimize and compare several steady-state and transient gradient-echo based qMRI methods, such as magnetic resonance fingerprinting (MRF), for jointT1andT2mapping. The impact of undersampling was also evaluated, assuming incoherent aliasing that is treated as noise by parameter estimation.In vivovalidation of the efficiency metric was also performed. Transient methods such as MRF can be up to 3.5 times more efficient than steady-state methods, when spatial undersampling is ignored. If incoherent aliasing is treated as noise during least-squares parameter estimation, the efficiency is reduced in proportion to the SNR of the data, with reduction factors of 5 often seen for practical SNR levels.In vivovalidation showed a very good agreement between the theoretical and experimentally predicted efficiency. This work presents and validates an efficiency metric to optimize and compare the performance of qMRI methods. Transient methods were found to be intrinsically more efficient than steady-state methods, however the effect of spatial undersampling can significantly erode this advantage.

Accelerated white matter lesion analysis based on simultaneous T 1 and T 2 ∗ quantification using magnetic resonance fingerprinting and deep learning

PURPOSE

To develop an accelerated postprocessing pipeline for reproducible and efficient assessment of white matter lesions using quantitative magnetic resonance fingerprinting (MRF) and deep learning.

METHODS

MRF using echo-planar imaging (EPI) scans with varying repetition and echo times were acquired for whole brain quantification of T 1 and T 2 ∗ in 50 subjects with multiple sclerosis (MS) and 10 healthy volunteers along 2 centers. MRF T 1 and T 2 ∗ parametric maps were distortion corrected and denoised. A CNN was trained to reconstruct the T 1 and T 2 ∗ parametric maps, and the WM and GM probability maps.

RESULTS

Deep learning-based postprocessing reduced reconstruction and image processing times from hours to a few seconds while maintaining high accuracy, reliability, and precision. Mean absolute error performed the best for T 1 (deviations 5.6%) and the logarithmic hyperbolic cosinus loss the best for T 2 ∗ (deviations 6.0%).

CONCLUSIONS

MRF is a fast and robust tool for quantitative T 1 and T 2 ∗ mapping. Its long reconstruction and several postprocessing steps can be facilitated and accelerated using deep learning.

Cardiac magnetic resonance fingerprinting: Trends in technical development and potential clinical applications

Quantitative cardiac magnetic resonance has emerged in recent years as an approach for evaluating a range of cardiovascular conditions, with T1 and T2 mapping at the forefront of these developments. Cardiac Magnetic Resonance Fingerprinting (cMRF) provides a rapid and robust framework for simultaneous quantification of myocardial T1 and T2 in addition to other tissue properties. Since the advent of cMRF, a number of technical developments and clinical validation studies have been reported. This review provides an overview of cMRF, recent technical developments, healthy subject and patient studies, anticipated technical improvements, and potential clinical applications. Recent technical developments include slice profile and pulse efficiency corrections, improvements in image reconstruction, simultaneous multislice imaging, 3D whole-ventricle imaging, motion-resolved imaging, fat-water separation, and machine learning for rapid dictionary generation. Future technical developments in cMRF, such as B0 and B1 field mapping, acceleration of acquisition and reconstruction, imaging of patients with implanted devices, and quantification of additional tissue properties are also described. Potential clinical applications include characterization of infiltrative, inflammatory, and ischemic cardiomyopathies, tissue characterization in the left atrium and right ventricle, post-cardiac transplantation assessment, reduction of contrast material, pre-procedural planning for electrophysiology interventions, and imaging of patients with implanted devices.

Magnetic resonance fingerprinting: from evolution to clinical applications

In 2013, Magnetic Resonance Fingerprinting (MRF) emerged as a method for fast, quantitative Magnetic Resonance Imaging. This paper reviews the current status of MRF up to early 2020 and aims to highlight the advantages MRF can offer medical imaging professionals. By acquiring scan data as pseudorandom samples, MRF elicits a unique signal evolution, or 'fingerprint', from each tissue type. It matches 'randomised' free induction decay acquisitions against pre-computed simulated tissue responses to generate a set of quantitative images of T1 , T2 and proton density (PD) with co-registered voxels, rather than as traditional relative T1 - and T2 -weighted images. MRF numeric pixel values retain accuracy and reproducibility between 2% and 8%. MRF acquisition is robust to strong undersampling of k-space. Scan sequences have been optimised to suppress sub-sampling artefacts, while artificial intelligence and machine learning techniques have been employed to increase matching speed and precision. MRF promises improved patient comfort with reduced scan times and fewer image artefacts. Quantitative MRF data could be used to define population-wide numeric biomarkers that classify normal versus diseased tissue. Certification of clinical centres for MRF scan repeatability would permit numeric comparison of sequential images for any individual patient and the pooling of multiple patient images across large, cross-site imaging studies. MRF has to date shown promising results in early clinical trials, demonstrating reliable differentiation between malignant and benign prostate conditions, and normal and sclerotic hippocampal tissue. MRF is now undergoing small-scale trials at several sites across the world; moving it closer to routine clinical application.

Fast and accurate calculation of myocardial T1 and T2 values using deep learning Bloch equation simulations (DeepBLESS)

PURPOSE

To propose and evaluate a deep learning model for rapid and accurate calculation of myocardial T1 /T2 values based on a previously proposed Bloch equation simulation with slice profile correction (BLESSPC) method.

METHODS

Deep learning Bloch equation simulations (DeepBLESS) models are proposed for rapid and accurate T1 estimation for the MOLLI T1 mapping sequence with balanced SSFP readouts and T1 /T2 estimation for a radial simultaneous T1 and T2 mapping (radial T1 -T2 ) sequence. The DeepBLESS models were trained separately based on simulated radial T1 -T2 and MOLLI data, respectively. The DeepBLESS T1 -T2 estimation accuracy was evaluated based on simulated data with different noise levels. The DeepBLESS model was compared with BLESSPC in simulation, phantom, and in vivo studies for the MOLLI sequence at 1.5 T and radial T1 -T2 sequence at 3 T.

RESULTS

After DeepBLESS was trained, in phantom studies, DeepBLESS and BLESSPC achieved similar accuracy and precision in T1 -T2 estimations for both MOLLI and radial T1 -T2 (P > .05). For in vivo, DeepBLESS and BLESSPC generated similar myocardial T1 /T2 values for radial T1 -T2 at 3 T (T1 : 1366 ± 31 ms for both methods, P > .05; T2 : 37.4 ms ± 0.9 ms for both methods, P > .05), and similar myocardial T1 values for the MOLLI sequence at 1.5 T (1044 ± 20 ms for both methods, P > .05). DeepBLESS generated a T1 /T2 map in less than 1 second.

CONCLUSION

The DeepBLESS model offers an almost instantaneous approach for estimating accurate T1 /T2 values, replacing BLESSPC for both MOLLI and radial T1 -T2 sequences, and is promising for multiparametric mapping in cardiac MRI.

T1, T2, and Fat Fraction Cardiac MR Fingerprinting: Preliminary Clinical Evaluation

BACKGROUND

Dixon cardiac magnetic resonance fingerprinting (MRF) has been recently introduced to simultaneously provide water T₁ , water T₂ , and fat fraction (FF) maps.

PURPOSE

To assess Dixon cardiac MRF repeatability in healthy subjects and its clinical feasibility in a cohort of patients with cardiovascular disease.

POPULATION

T1MES phantom, water-fat phantom, 11 healthy subjects and 19 patients with suspected cardiovascular disease.

STUDY TYPE

Prospective.

FIELD STRENGTH/SEQUENCE

1.5T, inversion recovery spin echo (IRSE), multiecho spin echo (MESE), modified Look-Locker inversion recovery (MOLLI), T₂ gradient spin echo (T₂ -GRASE), 6-echo gradient rewound echo (GRE), and Dixon cardiac MRF.

ASSESSMENT

Dixon cardiac MRF precision was assessed through repeated scans against conventional MOLLI, T₂ -GRASE, and PDFF in phantom and 11 healthy subjects. Dixon cardiac MRF native T₁ , T₂ , FF, postcontrast T₁ and synthetic extracellular volume (ECV) maps were assessed in 19 patients in comparison to conventional sequences. Measurements in patients were performed in the septum and in late gadolinium enhanced (LGE) areas and assessed using mean value distributions, correlation, and Bland-Altman plots. Image quality and diagnostic confidence were assessed by three experts using 5-point scoring scales.

STATISTICAL TESTS

Paired Wilcoxon rank signed test and paired t-tests were applied. Statistical significance was indicated by *(P < 0.05).

RESULTS

Dixon cardiac MRF showed good overall precision in phantom and in vivo. Septal average repeatability was ~23 msec for T₁ , ~2.2 msec for T₂ , and ~1% for FF. Biases in healthy subjects/patients were measured at +37 msec*/+60 msec* and -8.8 msec*/-8 msec* when compared to MOLLI and T₂ -GRASE, respectively. No statistically significant differences in postcontrast T₁ (P = 0.17) and synthetic ECV (P = 0.19) measurements were observed in patients.

DATA CONCLUSION

Dixon cardiac MRF attained good overall precision in phantom and healthy subjects, while providing coregistered T₁ , T₂ , and fat fraction maps in a single breath-hold scan with similar or better image quality than conventional methods in patients.

LEVEL OF EVIDENCE

2.

TECHNICAL EFFICACY STAGE

2.